Unsupervised Feature Learning Via Spectral Clustering of Multidimensional Patches for Remotely Sensed Scene Classification
By Fan Hu, Gui-Song Xia, Zifeng Wang, Xin Huang, Liangpei Zhang, Hong Sun. 2015
163 citations recorded by the source corpus.
Scene classification plays an important role in the interpretation of remotely sensed high-resolution imagery. However, the performance of scene classification strongly relies on the discriminative power of feature representation, which is generally hand-engineered and requires a huge amount of domain-expert knowledge as well as time-consuming hand tuning. Recently, unsupervised feature learning (UFL) provides an alternative way to automatically learn discriminative feature representation from images. However, the performances achieved by conventional UFL methods are not comparable to the state-of-the-art, mainly due to the neglect of locally substantial image structures. This paper presents an improved UFL algorithm based on spectral clustering, named UFL-SC, which cannot only adaptively learn good local feature representations but also discover intrinsic structures of local image patches. In contrast to the standard UFL pipeline, UFL-SC first maps the original image patches into a low-dimensional and intrinsic feature space by linear manifold analysis techniques, and then learns a dictionary (e.g., using K-means clustering) on the patch manifold for feature encoding. To generate a feature representation for each local patch, an explicit parameterized feature encoding method, i.e., triangle encoding, is applied with the learned dictionary on the same patch manifold. The holistic feature representation of image scenes is finally obtained by building a bag-of-visual-words (BOW) model of the encoded local features. Experiments demonstrate that the proposed UFL-SC algorithm can extract efficient local features for image scenes and show comparable performance to the state-of-the-art approach on open scene classification benchmark.
Subfields: Computer Vision and Pattern Recognition, Media Technology, Representation & Self-Supervised Learning, Remote Sensing
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Computer Vision and Pattern Recognition
In Media Technology
In Representation & Self-Supervised Learning
In Remote Sensing
Citations in the corpus
- Remote Sensing Image Scene Classification: Benchmark and State of the Art (2017, methodology): “been widely adopted to evaluate various different scene classification methods [9, 16, 18, 33, 37, 83-87, 97].”
- Deep learning in remote sensing: a review (2017, background): “The deep arhitectures discussed in the “Convolutional Neural Networks” section have been applied to the scene classification problem of high-resolution satellite images and led to state-of-the-art performance [71], [74], [80]–[87].”
- Deep Learning for Remote Sensing Data: A Technical Tutorial on the State of the Art (2016, methodology): “UnsUPerVised hierarchicaL FeatUre-LearninG-Based methods As indicated in the “General Framework” section, there is some work that focuses on unsupervised feature-learning techniques for RS images scene classification, such as sparse coding [58], k-means clustering [60], [109], and topic model [110],”
- Scene Classification via a Gradient Boosting Random Convolutional Network Framework (2016, methodology): “The traditional BoVW-based methods are mainly based on low-level features [2]–[5], and low-level features cannot precisely represent the semantics of the images because of the so-called semantic gap.”
- MARTA GANs: Unsupervised Representation Learning for Remote Sensing Image Classification (2016, methodology): “When the classification accuracy of our method is compared with LRFF [15] (an improved unsupervised feature learning algorithm based on spectral clustering), our method outperforms LRFF by more than 4%.”
- Scene classification of high resolution remote sensing images using convolutional neural networks (2016, methodology): “During the last decades, significant efforts have been made in developing various approaches for scene classification from satellite and aerial images [11, 15, 18-22].”
- Deep Unsupervised Embedding for Remotely Sensed Images Based on Spatially Augmented Momentum Contrast (2020, methodology): “[35] utilized a spectral clustering procedure to uncover the intrinsic structures among image patches.”
- Weakly Supervised Learning Based on Coupled Convolutional Neural Networks for Aircraft Detection (2016, background): “, scale-invariant feature transform (SIFT) and histogram of oriented gradients (HOG)]; construct a bag-of-visual-words representation or dictionary; and run a statistical classifier [7]– [10].”
- Training Deep Convolutional Neural Networks for Land–Cover Classification of High-Resolution Imagery (2017, background): “A variety of other features have also been used (see [4]–[6]), each with their respective advantages and drawbacks.”
- AID: A Benchmark Data Set for Performance Evaluation of Aerial Scene Classification (2016, methodology): “have been developed to automatically learn adaptive feature representations from images [20], [32], [37].”
- Fast Binary Coding for the Scene Classification of High-Resolution Remote Sensing Imagery (2016, methodology): “BOW [7] 71.86 SPM [30] 74 SCK [32] 72.52 SPCK++ [7] 77.38 SC + pooling [6] 81.67 ± 1.23 SG+ UFL [39] 82.72 ± 1.18 NFNC [71] 87.67 UFL-SC [40] 90.26 ± 1.51 COPD [12] 91.33 ± 1.11 ± 85.53 ± 1.24”
- Deep learning for remote sensing image classification: A survey (2018, methodology): “In recent years, learned high-level deep features have been reported to achieve state-of-the-art performance on aerial image classification (Hu et al., 2016, 2017; Xia et al., 2016; Yang et al., 2015; Zhao & Du, 2016).”
- Dirichlet-Derived Multiple Topic Scene Classification Model for High Spatial Resolution Remote Sensing Imagery (2016, methodology): “(BOVW) model [6]–[12] or the probabilistic topic model”